Edge Impulse Experts / AI-based Aquatic Air Bubble Detection with Ultrasonic Imaging
This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.
About this project
This neural network model with the Ridge classifier identifies toxic underwater air bubbles via aquatic ultrasonic scans (nondestructive inspection):
- bubble
- normal
After building my neural network model with the Ridge classifier, I deployed my advanced model as a fully optimized and customizable Arduino library and uploaded it to Nano ESP32. Also, I developed a web application from scratch to save the produced ultrasonic scan data buffers as samples and generate a pre-formatted CSV file as my data set.
Download block output
| Title | Type | Size | |
|---|---|---|---|
| CSV Wizard config | JSON file | 8 KB | |
| CSV Wizard uploaded file (scan_data_items.csv) | CSV file | 98 KB | |
| Raw data training data | NPY file | 50 windows | |
| Raw data training labels | NPY file | 50 windows | |
| Raw data testing data | NPY file | 10 windows | |
| Raw data testing labels | NPY file | 10 windows | |
| Classifier model | Pickle model | 2 KB | |
| Classifier model | Model evaluation metrics (JSON file) | 3 KB |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Summary
Data collected
1m 0sProject info
| Project ID | 366673 |
| Project version | 1 |
| License | Apache 2.0 |
